© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10084
    Prev
    Next
    INDEX
    Explanations

    dates in the 1600s

    oai_token-act-pair · gemini-2.0-flash

    Historical texts from 1600-1800s

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     '\\;'
    -0.78
     كومونز
    -0.68
    脚注の使い方
    -0.67
     "..\..\..\
    -0.59
    complexContent
    -0.56
    UALA
    -0.54
    itrile
    -0.54
    oursquare
    -0.54
    featureID
    -0.53
    migrationBuilder
    -0.52
    POSITIVE LOGITS
     república
    0.50
     koszulka
    0.50
     decorados
    0.48
     decorativos
    0.48
     fondament
    0.47
     chitar
    0.47
    libft
    0.47
     decorado
    0.47
     decorativo
    0.46
    nın
    0.46
    Activations Density 1.070%

    No Known Activations